CN115046566B - Path planning method and device for long-distance navigation and computer readable storage medium - Google Patents
Path planning method and device for long-distance navigation and computer readable storage medium Download PDFInfo
- Publication number
- CN115046566B CN115046566B CN202210962305.5A CN202210962305A CN115046566B CN 115046566 B CN115046566 B CN 115046566B CN 202210962305 A CN202210962305 A CN 202210962305A CN 115046566 B CN115046566 B CN 115046566B
- Authority
- CN
- China
- Prior art keywords
- path
- population
- initial
- optimal
- planning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a path planning method, a device and a computer-readable storage medium for long-distance navigation. The method comprises the following steps: dividing the source location to the destination location into a plurality of intervals according to the source location and the destination locationA segment; obtaining any one of a plurality of compartmentsLiThe relevance of each lane and the weight of each lane in the path planning; any one interval sectionLiAnd the weight input interval of each lane in the path planningLiCorresponding trained path planning model, and obtaining interval based on genetic algorithmLiThe optimal planned path of (2); and connecting the optimal planning path of each interval in the plurality of intervals to obtain a global optimal planning path from the source location to the destination location. According to the technical scheme, the global optimal path can be quickly obtained between long-distance source and destination points.
Description
Technical Field
The present application relates to the field of vehicle navigation, and more particularly, to a method, an apparatus, and a computer-readable storage medium for path planning for long-distance navigation.
Background
In the field of vehicle navigation, a path planning method for long-distance navigation is difficult. On the one hand, the long distance (e.g., across cities or across provinces) itself means various uncertainties of road conditions, and on the other hand, the long distance also means that a plurality of choices are faced when navigation planning is performed, which corresponds to a plurality of solutions for calculating roads in the navigation algorithm, and the cost is also required for selecting the optimal solution from the plurality of solutions. In the related art, the path planning method for long-distance navigation takes the whole long-distance path as an object, and directly solves a global optimal solution. Although the related art may obtain the optimal solution, i.e. the global optimal path, when the distance is long and the road condition is complex, it takes a lot of time to obtain the optimal solution in a very large solution space, and in most cases, it is difficult to solve.
Disclosure of Invention
In order to solve or partially solve the problems in the related art, the present application provides a path planning method, device and computer-readable storage medium for long-distance navigation, which can quickly obtain a global optimal path between long-distance source and destination points.
The first aspect of the present application provides a path planning method for long-distance navigation, including:
dividing the space between the source place and the destination place into a plurality of interval sections according to the source place and the destination place;
obtaining any one of the plurality of compartmentsLiAnd the weight of each lane in the path plan;
any one of the spacing segmentsLiAnd the weight of each lane in the path planning is input into the interval sectionLiA corresponding trained path planning model, the interval being obtained based on a genetic algorithmLiThe optimal planned path of (2);
and connecting the optimal planning path of each interval segment in the plurality of interval segments to obtain a global optimal planning path from the source point to the destination point.
A second aspect of the present application provides a path planning apparatus for long-distance navigation, including:
the segmentation module is used for dividing the space between the source place and the destination place into a plurality of interval sections according to the source place and the destination place;
an acquisition module for acquiring any one of the plurality of compartmentsLiAnd the weight of each lane in the path plan;
a computing module for dividing said arbitrary one of said compartmentsLiAnd the weight of each lane in the path planning is input into the interval sectionLiA corresponding trained path planning model, the interval section is obtained based on genetic algorithmLiThe optimal planned path of (2);
and the connection module is used for connecting the optimal planning path of each interval in the plurality of intervals to obtain a global optimal planning path from the source location to the destination location.
A third aspect of the present application provides an electronic device comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon executable code, which, when executed by a processor of an electronic device, causes the processor to perform the method as described above.
The technical scheme provided by the application can comprise the following beneficial effects: in obtaining any one of a plurality of compartmentsLiAfter the weight of each lane in the path planning, the arbitrary one is divided into sectionsLiAnd the weight input interval of each lane in the path planningLiA corresponding trained path planning model for obtaining the interval based on genetic algorithmLiAnd finally, connecting the optimal planned path of each interval segment in the plurality of interval segments to obtain a global optimal planned path from the source point to the destination point. Compared with the prior art that the whole long-distance path is taken as an object and the global optimal solution is directly solved, the method divides the path from the source point to the destination point into a plurality of interval segments before the path is planned, obtains the optimal path plan for each interval segment based on the genetic algorithm by combining the trained path planning model, and is equivalent to searching the optimal solution in a smaller solution space every time, so that the global optimal path can be quickly obtained between the long-distance source and destination points.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a schematic flowchart of a path planning method for long-distance navigation according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a path planning apparatus for long-distance navigation according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the accompanying drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the field of vehicle navigation, a path planning method for long-distance navigation is difficult. On the one hand, the long distance (e.g., across cities or across provinces) itself means various uncertainties of road conditions, and on the other hand, the long distance also means that a plurality of choices are faced when navigation planning is performed, which corresponds to a plurality of solutions for calculating roads in the navigation algorithm, and the cost is also required for selecting the optimal solution from the plurality of solutions. In the related art, the path planning method for long-distance navigation takes the whole long-distance path as an object, and directly solves the global optimal solution. Although the related art may obtain the optimal solution, i.e. the global optimal path, when the distance is long and the road condition is complex, it takes a lot of time to obtain the optimal solution in a very large solution space, and in most cases, it is difficult to solve.
In order to solve the above problem, the embodiments of the present application provide a path planning method for long-distance navigation, which can quickly obtain a global optimal path between long-distance source and destination points.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of a path planning method for long-distance navigation shown in the embodiment of the present application is shown, which mainly includes steps S101 to S104, and is described as follows:
step S101: the source to destination points are divided into a plurality of intervals according to the source point and the destination point.
The source location is a starting location in the long-distance target navigation segment and the destination location is a target location in the long-distance target navigation segment. For example, if the vehicle needs to travel from city B of province a to city D of province C, city B is the source point and city D is the destination point. In the embodiment of the present application, the division between the source location and the destination location has certain flexibility, and the division between the source location and the destination location may be divided into a plurality of intervals according to the distance, for example, the division between the source location and the destination location is divided into a plurality of intervals according to one interval of 50 kilometers; the interval between the source point and the destination point can also be divided according to the actual existing city between the source point and the destination point, a specific building and the like for the end point division basis of each interval, for example, five cities of A, B, C, D and E exist between the source point and the destination point, a and B can be divided into one interval by taking B and C as the head and tail end points, one interval by taking C and D as the head and tail end points, one interval by taking D and E as the head and tail end points, and the like.
Step S102: obtaining any one of a plurality of compartmentsLiAnd the weight of each lane in the path plan.
In the embodiment of the application, the relevance between the lanes comprises the longitude and latitude of the driving entrance of the lane, the longitude and latitude of the driving exit, whether the lanes can be changed or not and the like, and the weight of each lane in the path planning is determined by the grade, the type and the like of the lane, for example, the grade of a main lane is higher than that of a side road lane, and the weight of the main lane is greater than that of the side road lane in the path planning; as another example, lanes of an expressway have a greater weight in path planning than lanes of a provincial highway, and so on; in addition, the length, safety, smoothness, etc. of the path corresponding to the lane may also be used as a measure of the lane weight.
Step S103: any one interval sectionLiAnd the weight input interval of each lane in the path planningLiA corresponding trained path planning model for obtaining the interval based on genetic algorithmLiThe optimal planned path.
In the embodiment of the application, the trained path planning model is a path planning model obtained by training a deep learning model by adopting a genetic algorithm. After the trained path planning model is obtained through training, any interval is divided into segmentsLiAnd weight input interval in path planningLiThe corresponding trained path planning model can obtain interval segments based on genetic algorithmLiThe optimal planned path.
As an example of the present application, the interval is obtained based on a genetic algorithmLiThe optimal planned route of (3) can be realized through steps Sa1031 to Sa1034, which are described in detail as follows:
step Sa1031: from the interval sectionLiStarting from the starting point, obtaining the interval from the starting pointLiThe shortest initial path of the destination point of (4) is used as the initial population.
In particular, the segments may be spaced fromLiStarting from the starting point, randomly selecting a place adjacent to the starting point as a next path point, wherein the path point requires the shortest distance to the destination point, and repeating the steps until the destination point is found, namely obtaining an initial path, and generating an initial population. To prevent loops, the same location has and can only pass once.
Step Sa1032: combining spacers for the initial populationLiAnd calculating the fitness value of each individual lane according to the relevance of each lane and the weight of each lane in the path planning.
In genetic algorithms, fitness value (fitness) of an individual refers to a measure of how dominant the individual is in the population's survival, distinguishing between "good" and "bad" individuals. The fitness value is calculated by using a fitness function (fitness function), which is also called an evaluation function, and the fitness of an individual is judged mainly through individual characteristics; the greater the fitness value for an individual, the greater the likelihood that the individual is retained. For example, in the embodiment of the present application, the path length, the path safety degree, the path smoothness and the convenience of lane change between lanes corresponding to lanes may be used as evaluation indexes of a corresponding path fitness function, and an individual, that is, a fitness value of a path may be calculated.
Step Sa1033: and according to the fitness value of the individual, performing selection, crossing and mutation operations on the population to obtain a new population.
As an embodiment of the present application, according to the fitness value of an individual, selecting, crossing and mutating the population, and obtaining a new population may be: randomly selecting two individuals from the population to carry out fitness value comparison, wherein the individuals with higher fitness value enter the next generation, and the individuals with lower fitness value are discarded; selecting two chromosomes to be crossed at a common node of the two chromosomes to form a path, and if the two chromosomes do not have the common node, not carrying out the crossing operation; randomly selecting individuals to be mutated from the contemporary population, deleting the genetic units at the corners of the path, randomly selecting one genetic unit around the deleted genetic unit for replacement, and reconnecting to form a new path. In the embodiment, the selection of the population individuals is a selection based on a local competition mechanism, and only the comparison of the relative values of the fitness is carried out, so that certain randomness is provided, local optimization is avoided, the phenomena of premature convergence and stagnation are avoided to a certain extent, one genetic unit around the deleted genetic unit is randomly selected for replacement, and a certain path is prevented from being changed into an invalid path, so that the complexity of the algorithm is reduced, and the calculation time of the algorithm is shortened. It should be noted that, in the embodiment of the present application, the population refers to a population composed of individuals representing individually planned paths, and the chromosome is a feasible solution of the genetic algorithm, and a path representing a final planned path is determined with a high probability during each evolution process of the population.
Step Sa1034: executing a path optimization strategy on the new population to obtain a compartmentLiThe optimal planned path.
Specifically, one of the places between the same place numbers and the same place may be deleted, and the formed new path may be used as the next generation population individual; for another example, two nodes are added at two ends of a corner between paths, and if the connected path does not pass through an obstacle, the original path is replaced by the path, and the nodes at the original corner are deleted, so that a smoother new path is generated, and the like. If the difference of the fitness value between the two generation individuals does not exceed the preset fitness threshold value, the current generation path is output as a spacing segmentLiThe optimal planned path.
As another embodiment of the present application, the spacer is obtained based on a genetic algorithmLiThe optimal planned path can be realized through steps Sb1031 to Sb1034, which are described in detail as follows:
step Sb1031: an initial population is rapidly generated to which both individual diversity and pathway are accessible.
Specifically, the rapid generation of the initial population with individual diversity and path access can be realized by the following steps S1 to S5:
step S1: initializing a random tree, and respectively taking root nodes of two subtrees in the random tree as a starting point and an end point;
step S2: randomly selecting a point in the driving range of a vehiclePrandAs a growing direction, all nodes and points of a sub-tree of the random tree are computedPrandThe Euclidean distance between the nodes is found out, and the node with the minimum Euclidean distance is found outPlstThe sub-tree slave nodePlstBegin with growth factors towards the pointPrandGrow new nodesPnewNew node will bePnewConnecting to a subtree;
and step S3: node of two subtrees in random tree with one of the subtrees growing freely with the otherPnewGrowing new nodes in the same free growth process in the growth directionP’newNew node will beP’newConnecting into a subtree;
and step S4: judging whether the random tree establishes a sufficient number of connections between the starting point and the end point, if so, stopping growing and entering the step S5, otherwise, returning to the step S2 to continue growing;
step S5: and taking the connecting point of the random tree as an initial point of the upward tracing, and performing the upward tracing for multiple times towards the root node of the random tree until the upward tracing reaches the root node, wherein the accessible paths generated by the multiple upward tracing form an initial population.
When tracing back multiple times towards the root node of the random tree, the nodes and edges in the tree that the tracing back goes through may form reachable paths.
Step Sb1032: combining spacers for the initial populationLiAnd calculating the fitness value of each individual lane according to the relevance of each lane and the weight of each lane in the path planning.
Here, the implementation of step Sb1032 is similar to the implementation process of step Sa1032 in the foregoing embodiment, and reference may be made to the relevant description of the foregoing embodiment, which is not repeated herein.
Step Sb1033: according to the fitness value of an individual, the initial population is evolved by adopting selection, crossing and variation to obtain interval segmentsLiThe initial optimal planned path.
Here, the implementation of step Sb1033 is similar to the implementation process of step Sa1033 in the foregoing embodiment, and reference may be made to the relevant description of the foregoing embodiment, which is not repeated herein.
Step Sb1034: taking key points of the initial optimal planned path as control points, and smoothing the initial optimal planned path through N times of B-spline curve algorithm to obtain interval segmentsLiTo the final optimal planned path.
Here, the nth-order B-spline curve may be a quadratic B-spline curve.
As another embodiment of the present application, the spacer is obtained based on a genetic algorithmLiThe optimal planned path can be realized through steps Sc1031 to Sc1037, which are described in detail as follows:
step Sc1031: and determining the initial population quantity Ng, the maximum optimized population algebra Nmax, a starting point S and an end point T.
Step Sc1032: ng initial paths are generated between the starting point S and the end point T.
The number of initial paths is equal to the number of initial populations, and is Ng.
Step Sc1033: the generated initial path is optimized in combination with a bezier curve.
The reason why the generated initial path is optimized by combining the Bezier curve is that the path can be smoother by optimizing the generated initial path by adopting the Bezier curve in consideration of the problems that path segments with large curvature, redundant nodes and the like are easy to generate when the path planning is carried out by the traditional genetic algorithm. In particular, bezier curves may be introduced into genetic algorithms; and obtaining a Bezier curve with m control points by taking each point with larger curvature change in the initialized path of the genetic algorithm as the control points P0, P1, P2, … and Pm. Here, the point with a large change in curvature means that the curvature corresponding to a certain point in the path exceeds a preset curvature threshold.
Step Sc1034: and calculating the fitness function value of each path by adopting the fitness function with the safety guarantee distance and the punishment factor in combination with the relevance among the lanes and the weight of each lane in path planning.
If the fitness function only uses the path length as the main criterion for selecting the path, the shortest path can be ensured, but the path may have a problem of collision due to the fact that the distance between the vehicle and the obstacle is too small. The application provides an adaptability function based on safety guarantee by increasing factors such as safety guarantee distance placement, punishment and the like. The higher the penalty is as the distance between the path and the obstacle is closer. Therefore, adaptive adjustment of the fitness function can be realized, so that the quality of the planned path is improved.
Step Sc1035: selection, crossover and mutation operations are performed to generate new paths.
Here, the implementation of step Sc1035 is similar to the implementation process of step Sa1032 or step Sb1032 in the foregoing embodiment, and reference may be made to the relevant description of the foregoing embodiment, which is not repeated herein.
Step Sc1036: and judging whether the current optimal value reaches the maximum optimized population algebra, if so, stopping the algorithm and turning to a step Sc1037, and if not, updating the path and turning to a step Sc1033.
Step Sc1037: outputting the corresponding path as the interval segment when the current optimal value reaches the maximum optimized population algebraLiThe optimal planned path.
Step S104: and connecting the optimal planning path of each interval in the plurality of intervals to obtain a global optimal planning path from the source location to the destination location.
Since the steps S101 to S103 are performed on any one of the plurality of compartmentsLiThe optimal path is planned, and therefore, the optimal planned path for each of the plurality of bays can be obtained through steps S101 to S103. And then, connecting the optimal planning path of each interval segment in the plurality of interval segments to obtain a global optimal planning path from the source point to the destination point.
As can be seen from the above-mentioned path planning method for long-distance navigation illustrated in fig. 1, any one of the plurality of compartments is obtainedLiAfter the weight of each lane in the path planning, the arbitrary one is divided into sectionsLiAnd the weight input interval of each lane in the path planningLiA corresponding trained path planning model for obtaining the interval based on genetic algorithmLiOptimal planned path ofAnd then connecting the optimal planning path of each interval section in the plurality of interval sections to obtain a global optimal planning path from the source point to the destination point. Compared with the prior art that the whole long-distance path is taken as an object and the global optimal solution is directly solved, the method divides the path from the source point to the destination point into a plurality of interval segments before the path is planned, obtains the optimal path plan for each interval segment based on the genetic algorithm by combining the trained path planning model, and is equivalent to searching the optimal solution in a smaller solution space every time, so that the global optimal path can be quickly obtained between the long-distance source and destination points.
Corresponding to the embodiment of the application function implementation method, the application also provides a path planning device for long-distance navigation, electronic equipment and a corresponding embodiment.
Fig. 2 is a schematic structural diagram of a path planning apparatus for long-distance navigation according to an embodiment of the present application. For convenience of explanation, only portions related to the embodiments of the present application are shown. The path planning apparatus for long-distance navigation illustrated in fig. 2 mainly includes a segmentation module 201, an acquisition module 202, a calculation module 203, and a connection module 204, where:
a segmentation module 201, configured to divide a space between a source point and a destination point into a plurality of interval segments according to the source point and the destination point;
an acquisition module 202 for acquiring any one of a plurality of compartmentsLiThe relevance of each lane and the weight of each lane in the path planning;
a calculation module 203 for dividing any one of the compartmentsLiAnd the weight input interval of each lane in the path planningLiA corresponding trained path planning model for obtaining the interval based on genetic algorithmLiThe optimal planned path of (2);
the connection module 204 is configured to connect the optimal planned path of each of the multiple compartments to obtain a global optimal planned path from the source location to the destination location.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
As can be seen from the above-mentioned path planning apparatus for long-distance navigation illustrated in fig. 2, any one of the plurality of compartments is obtainedLiAfter the weight of each lane in the path planning, the arbitrary one is divided into sectionsLiAnd the weight input interval of each lane in the path planningLiA corresponding trained path planning model for obtaining the interval based on genetic algorithmLiAnd finally, connecting the optimal planned path of each interval segment in the plurality of interval segments to obtain a global optimal planned path from the source point to the destination point. Compared with the prior art that the whole long-distance path is taken as an object and the global optimal solution is directly solved, the method divides the path from the source point to the destination point into a plurality of interval segments before the path is planned, obtains the optimal path plan for each interval segment based on the genetic algorithm by combining the trained path planning model, and is equivalent to searching the optimal solution in a smaller solution space every time, so that the global optimal path can be quickly obtained between the long-distance source and destination points.
Fig. 3 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 3, the electronic device 300 includes a memory 310 and a processor 320.
Processor 320 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 310 may include various types of storage units such as a system memory, a Read Only Memory (ROM), and a permanent storage device. Wherein the ROM may store static data or instructions for the processor 320 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 310 may comprise any combination of computer-readable storage media, including various types of semiconductor memory chips (e.g., DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 310 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 310 has stored thereon executable code that, when processed by the processor 320, may cause the processor 320 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) having executable code (or a computer program or computer instruction code) stored thereon, which, when executed by a processor of an electronic device (or server, etc.), causes the processor to perform part or all of the steps of the above-described methods according to the present application.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or improvements to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (7)
1. A path planning method for long-distance navigation is characterized by comprising the following steps:
dividing the space between the source place and the destination place into a plurality of interval sections according to the source place and the destination place;
obtaining any one of the plurality of compartmentsLiAnd the weight of each lane in the path planning;
any one of the spacing segmentsLiAnd the weight of each lane in the path planning is input into the interval sectionLiA corresponding trained path planning model, the interval being obtained based on a genetic algorithmLiThe optimal planned path of (2);
connecting the optimal planning path of each interval segment in the plurality of interval segments to obtain a global optimal planning path from the source point to the destination point;
the genetic algorithm-based derivation of the spacerLiThe optimal planned path of (2), comprising: from the spacer sectionLiStarting from the starting point, obtaining the interval section from the starting pointLiIs shortest of the destination point ofIs an initial population; combining said compartments for said initial populationLiCalculating the fitness value of each individual by the relevance of each lane and the weight of each lane in the path planning; according to the fitness value of the individual, selecting, crossing and mutating the population to obtain a new population; executing a path optimization strategy on the new population to obtain the interval sectionLiThe optimal planned path of (2); or
The genetic algorithm-based derivation of the spacerLiThe optimal planned path of (2), comprising: rapidly generating an initial population which is accessible to individual diversity and paths; combining said compartments for said initial populationLiCalculating the fitness value of each individual through the relevance of each lane and the weight of each lane in the path planning; according to the fitness value of the individual, evolving the initial population by adopting selection, crossing and variation to obtain the interval segmentLiThe initial optimal planned path of (1); taking the key points of the initial optimal planned path as control points, and smoothing the initial optimal planned path through N-time B-spline curve algorithm to obtain the interval segmentLiThe final optimal planned path; or
The genetic algorithm-based derivation of the spacerLiThe optimal planned path of (2), comprising: step S1: determining the number Ng of initial populations, the maximum optimized population algebra Nmax, a starting point S and a terminating point T; step S2: generating Ng initial paths between the starting point S and the end point T; and step S3: optimizing the generated initial path in combination with a Bezier curve; and step S4: calculating a fitness function value of each path by adopting a fitness function with safety guarantee distance and punishment factors in combination with the relevance among the lanes and the weight of the lanes in path planning; step S5: performing selection, crossing and mutation operations to generate new paths; step S6: judging whether the current optimal value reaches the maximum optimized population generation number Nmax, if so, stopping the algorithm and turning to the step S7, otherwise, updating the path and turning to the step S3; step S7: outputting the corresponding path when the current optimal value reaches the maximum optimized population algebra as the interval sectionLiThe optimal planned path.
2. The method for planning a path for long-distance navigation according to claim 1, wherein the selecting, crossing and mutating the population according to the fitness value of the individual to obtain a new population comprises:
randomly selecting two individuals from the population to carry out fitness value comparison, wherein the individuals with higher fitness value enter the next generation, and the individuals with lower fitness value are discarded;
selecting two chromosomes to be crossed at a common node of the two chromosomes to form a path, and if the two chromosomes do not have the common node, not carrying out the crossing operation;
randomly selecting an individual to be mutated from the contemporary population, deleting the genetic units at the turning of the path, randomly selecting a genetic unit around the deleted genetic unit for substitution, and re-connecting to form the new path.
3. The method for planning the path of the long-distance navigation according to claim 1, wherein the rapidly generating an initial population with individual diversity and path access comprises:
step S1: initializing a random tree, and respectively taking root nodes of two subtrees in the random tree as a starting point and an end point;
step S2: randomly selecting a point in the driving range of a vehiclePrandCalculating all nodes and points of a sub-tree of the random tree as a growing directionPrandThe Euclidean distance between the nodes is found out, and the node with the minimum Euclidean distance is found outPlstSaid sub-tree being from said nodePlstBegin with growth factors towards the pointPrandGrow new nodesPnewThe new node is addedPnewConnecting into a subtree;
and step S3: nodes of one of the two subtrees in the random tree growing freely in the other subtreePnewIn the growth direction, new nodes grow out in the same free growth processP’newNew node will beP’newConnecting into a subtree;
and step S4: judging whether the random tree establishes a sufficient number of connections between the starting point and the end point, if so, stopping growing and entering the step S5, otherwise, returning to the step S2 to continue growing;
step S5: and taking the connection point of the random tree as an initial point of upward tracing, and performing multiple upward tracing towards the root node of the random tree until the random tree is traced to the root node, wherein accessible paths generated by the multiple upward tracing form the initial population.
4. The method for path planning for long-range navigation according to claim 1, wherein the optimizing the generated initial path in combination with the bezier curve comprises:
introducing a bezier curve into the genetic algorithm;
and obtaining a Bezier curve with m control points by taking each point with larger curvature change in the initialized path of the genetic algorithm as the control points P0, P1, P2, … and Pm.
5. A path planning apparatus for long-distance navigation, the apparatus comprising:
the segmentation module is used for dividing the space between the source place and the destination place into a plurality of interval sections according to the source place and the destination place;
an acquisition module for acquiring any one of the plurality of compartmentsLiAnd the weight of each lane in the path planning;
a computing module for dividing said arbitrary one of said compartmentsLiAnd the weight of each lane in the path planning is input into the interval sectionLiA corresponding trained path planning model, the interval being obtained based on a genetic algorithmLiThe optimal planned path of (2);
the connection module is used for connecting the optimal planning path of each interval in the plurality of intervals to obtain a global optimal planning path from the source location to the destination location;
the genetic algorithm-based derivation of the spacerLiThe optimal planned path of (1), comprising: from the said spacerLiStarting from the starting point, obtaining the interval section from the starting pointLiThe shortest initial path of the destination point is used as an initial population; combining said compartments for said initial populationLiCalculating the fitness value of each individual through the relevance of each lane and the weight of each lane in the path planning; according to the fitness value of the individual, selecting, crossing and mutating the population to obtain a new population; executing a path optimization strategy on the new population to obtain the interval sectionLiThe optimal planned path of (2); or
The genetic algorithm-based derivation of the spacerLiThe optimal planned path of (1), comprising: rapidly generating an initial population which is accessible to individual diversity and paths; combining said compartments for said initial populationLiCalculating the fitness value of each individual by the relevance of each lane and the weight of each lane in the path planning; according to the fitness value of the individual, evolving the initial population by adopting selection, crossing and variation to obtain the interval segmentLiThe initial optimal planned path of (1); taking the key points of the initial optimal planned path as control points, and smoothing the initial optimal planned path through N-time B-spline curve algorithm to obtain the interval segmentLiThe final optimal planned path; or
The genetic algorithm-based derivation of the spacerLiThe optimal planned path of (1), comprising: step S1: determining the number Ng of initial populations, the maximum optimized population algebra Nmax, a starting point S and a terminating point T; step S2: generating Ng initial paths between the starting point S and the end point T; and step S3: optimizing the generated initial path in combination with a Bezier curve; and step S4: calculating a fitness function value of each path by adopting a fitness function with safety guarantee distance and punishment factors in combination with the relevance among the lanes and the weight of the lanes in path planning; step S5: performing selection, crossing and mutation operations to generate new paths; step S6: judgmentJudging whether the current optimal value reaches the maximum optimized population algebra Nmax, if so, stopping the algorithm and turning to the step S7, otherwise, updating the path and turning to the step S3; step S7: outputting the corresponding path when the current optimal value reaches the maximum optimized population algebra as the interval sectionLiThe optimal planned path.
6. An electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon executable code which, when executed by a processor of an electronic device, causes the processor to perform the method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210962305.5A CN115046566B (en) | 2022-08-11 | 2022-08-11 | Path planning method and device for long-distance navigation and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210962305.5A CN115046566B (en) | 2022-08-11 | 2022-08-11 | Path planning method and device for long-distance navigation and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115046566A CN115046566A (en) | 2022-09-13 |
| CN115046566B true CN115046566B (en) | 2022-10-28 |
Family
ID=83167917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210962305.5A Active CN115046566B (en) | 2022-08-11 | 2022-08-11 | Path planning method and device for long-distance navigation and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115046566B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10219500A1 (en) * | 2002-04-30 | 2003-11-20 | Siemens Ag | Navigation system with dynamic route planning |
| US7110881B2 (en) * | 2003-10-07 | 2006-09-19 | Deere & Company | Modular path planner |
| JP5111084B2 (en) * | 2007-12-12 | 2012-12-26 | クラリオン株式会社 | Navigation device |
| CN102954799A (en) * | 2011-08-29 | 2013-03-06 | 环达电脑(上海)有限公司 | Rapid path programming navigation device and method |
| TW201614195A (en) * | 2014-10-02 | 2016-04-16 | Inst Information Industry | Route planning system, route planning method and traffic information update method |
| CN108267144A (en) * | 2016-12-30 | 2018-07-10 | 沈阳美行科技有限公司 | A kind of navigation routine recommends method, system and its apparatus |
| US10837789B2 (en) * | 2018-08-30 | 2020-11-17 | Wipro Limited | Method and system for determining an optimal path for navigation of a vehicle |
| CN110530387A (en) * | 2019-09-02 | 2019-12-03 | 上海图聚智能科技股份有限公司 | Paths planning method, device, electronic equipment and storage medium |
| CN110530393A (en) * | 2019-10-08 | 2019-12-03 | 北京邮电大学 | Lane grade paths planning method, device, electronic equipment and readable storage medium storing program for executing |
| CN113728212B (en) * | 2020-03-26 | 2024-05-28 | 百度时代网络技术（北京）有限公司 | Navigation route planning method for automatic driving vehicle |
-
2022
- 2022-08-11 CN CN202210962305.5A patent/CN115046566B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115046566A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111415048B (en) | Vehicle path planning method based on reinforcement learning | |
| US9536146B2 (en) | Determine spatiotemporal causal interactions in data | |
| CN101409011B (en) | Method, apparatus and system for matching map and conferring route | |
| CN104215254B (en) | The method and apparatus of path navigation | |
| CN104266656A (en) | Method and device for searching shortest path of road network | |
| CN112013829A (en) | Multi-UAV/UGV (unmanned aerial vehicle/user generated Unit) cooperative long-term operation path planning method based on multi-objective optimization | |
| CN114162140B (en) | Optimal lane matching method and system | |
| CN112985371A (en) | Path determination method, device and equipment | |
| CN111189455B (en) | Unmanned aerial vehicle route planning method, system and storage medium | |
| CN114399125B (en) | Motorcade optimal trajectory control method and device, electronic equipment and storage medium | |
| CN114722482A (en) | Method for predicting deformation of plateau tunnel and plateau tunnel health detection system | |
| CN112330054B (en) | Dynamic travel business problem solving method, system and storage medium based on decision tree | |
| CN115046566B (en) | Path planning method and device for long-distance navigation and computer readable storage medium | |
| CN116817958B (en) | Reference path generation method, device and medium based on barrier grouping | |
| CN109190787B (en) | Dual particle swarm multi-monitoring point access path planning method for underwater vehicle | |
| Rice et al. | Exact graph search algorithms for generalized traveling salesman path problems | |
| CN117308985A (en) | Vehicle path planning method, device, equipment and medium oriented to load constraint | |
| CN116820110B (en) | Ecological environment monitoring task planning method and device based on intelligent optimization algorithm | |
| CN117291323A (en) | Vehicle path optimization method, device, equipment and medium based on quantum algorithm | |
| CN115424446B (en) | Road network topology simplification method for traffic organization evaluation | |
| CN114996278B (en) | Road network shortest path distance query method based on reinforcement learning | |
| CN107982917B (en) | Character path searching method for 3D game | |
| Jagadeesh et al. | Route computation in large road networks: a hierarchical approach | |
| CN112785082A (en) | Learning-based road network shortest path distance approximate calculation model training method and device | |
| Kim et al. | Finding realistic shortest path in road networks with lane changing and turn restriction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |